Logical Optimal Actions (LOA)

Logical Optimal Actions (LOA) is an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural network and symbolic knowledge acquisition approach for natural language interaction games. This repository has an implementation of LOA experiments consists of Python package on TextWorld Commonsense (TWC) game.

Please check and execute the following repo.

Daiki Kimura, Subhajit Chaudhury, Sarathkrishna Swaminathan, Don Joven Agravante, Michiaki Tatsubori, Asim Munawar